Cost-aware Pre-training for Multiclass Cost-sensitive Deep Learning

Abstract

Deep learning has been one of the most prominent machine learning techniques nowadays, being the state-of-the-art on a broad range of applications where automatic feature extraction is needed. Many such applications also demand varying costs for different types of mis-classification errors, but it is not clear whether or how such cost information can be incorporated into deep learning to improve performance. In this work, we propose a novel cost-aware algorithm that takes into account the cost information into not only the training stage but also the pre-training stage of deep learning. The approach allows deep learning to conduct automatic feature extraction with the cost information effectively. Extensive experimental results demonstrate that the proposed approach outperforms other deep learning models that do not digest the cost information in the pre-training stage.

References in corpus (2)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Caffe: Convolutional Architecture for Fast Feature Embedding

Cited by in corpus (6)

• A systematic study of the class imbalance problem in convolutional neural networks
• Remix: Rebalanced Mixup
• Cost-Sensitive Deep Learning with Layer-Wise Cost Estimation
• On Class Imbalance and Background Filtering in Visual Relationship Detection
• Time Series Classification Using Convolutional Neural Network On Imbalanced Datasets
• CRCEN: A Generalized Cost-sensitive Neural Network Approach for Imbalanced Classification